Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / espnet/espnet_model_zoo issues and pull requests
#80 - Problem with very short and noisy audio during inference when providing xvector embeddings
Issue -
State: open - Opened by Phlayne 5 months ago
- 1 comment
#79 - installing on mac silicon py 3.11.4 - sentencepiece building
Issue -
State: open - Opened by willwade 7 months ago
- 1 comment
#78 - I want to add an original model to "table.csv", but it says I don't have permission and I can't push.
Issue -
State: open - Opened by c44128 10 months ago
#77 - Add TF-GridNet and TD-SpeakerBeam to table.csv
Pull Request -
State: open - Opened by Emrys365 over 1 year ago
- 1 comment
#76 - Huggingface downloader / cache, offline mode
Issue -
State: open - Opened by bmilde over 1 year ago
- 1 comment
#75 - [SVS] Update table.csv
Pull Request -
State: open - Opened by A-Quarter-Mile over 1 year ago
#74 - Redundant ljspeech vits models
Issue -
State: open - Opened by kelseyjd over 1 year ago
- 3 comments
#73 - FileNotFoundError
Issue -
State: closed - Opened by Superman-Valencia over 1 year ago
- 4 comments
#72 - librosa.util.exceptions.ParameterError: Window size mismatch: 512 != 400 when using streaming transformer model
Issue -
State: closed - Opened by bmilde almost 2 years ago
- 2 comments
#71 - Update setup.py
Pull Request -
State: closed - Opened by sw005320 almost 2 years ago
#70 - Add reazon-research/reazonspeech-espnet-v1
Pull Request -
State: closed - Opened by fujimotos almost 2 years ago
- 8 comments
#69 - TypeError: init() got an unexpected keyword argument 'train_config'
Issue -
State: open - Opened by MUFCLK about 2 years ago
- 1 comment
#68 - Missing getitem on huggingface page:
Issue -
State: open - Opened by boeddeker about 2 years ago
#67 - ModuleNotFoundError: No module named 'espnet_model_zoo.downloader'; 'espnet_model_zoo' is not a package
Issue -
State: open - Opened by neso613 over 2 years ago
- 1 comment
#66 - Using an original model trained in espnet1
Issue -
State: open - Opened by supernaiter over 2 years ago
- 6 comments
#65 - 'Speech2Text' has no attribute 'from_pretrained'
Issue -
State: closed - Opened by v-yunbin over 2 years ago
- 6 comments
#64 - add some pretrained enh models
Pull Request -
State: closed - Opened by LiChenda over 2 years ago
#63 - support direct huggingface url specification
Pull Request -
State: closed - Opened by kan-bayashi over 2 years ago
#62 - add pre-trained skim model
Pull Request -
State: closed - Opened by LiChenda over 2 years ago
#61 - Add a multi-channel speech enhancement model
Pull Request -
State: closed - Opened by Emrys365 almost 3 years ago
#60 - Add Google speechcommands (12 and 35 commands) (SLU)
Pull Request -
State: closed - Opened by pyf98 almost 3 years ago
- 1 comment
#59 - Update README.md
Pull Request -
State: closed - Opened by sw005320 almost 3 years ago
- 1 comment
#58 - Update README.md
Pull Request -
State: closed - Opened by sw005320 almost 3 years ago
- 1 comment
#57 - Add streaming Transformer model using tedlium2
Pull Request -
State: closed - Opened by D-Keqi about 3 years ago
- 12 comments
#56 - Add SLU models
Pull Request -
State: open - Opened by siddhu001 about 3 years ago
- 8 comments
#55 - CSJ's pretrained conformer-based ASR model on zenodo
Issue -
State: closed - Opened by feddybear about 3 years ago
- 1 comment
#54 - Fix table.csv
Pull Request -
State: closed - Opened by kan-bayashi about 3 years ago
- 1 comment
#53 - Add TTS models
Pull Request -
State: closed - Opened by kan-bayashi about 3 years ago
- 1 comment
#52 - Uploading ESPnet2 model to Zenodo
Issue -
State: open - Opened by DanBerrebbi about 3 years ago
- 6 comments
#51 - Add pretrained models
Pull Request -
State: closed - Opened by kan-bayashi about 3 years ago
- 1 comment
#50 - Is it possible to upload some pretrained models of tacotron2 for the libritts dataset?
Issue -
State: closed - Opened by guoaoo about 3 years ago
- 2 comments
#49 - Add filelock for all writing functions
Pull Request -
State: closed - Opened by kamo-naoyuki about 3 years ago
- 1 comment
#48 - Add VITS models
Pull Request -
State: closed - Opened by kan-bayashi about 3 years ago
#47 - Add JSUT VITS model
Pull Request -
State: closed - Opened by kan-bayashi about 3 years ago
- 1 comment
#46 - Update README for espnet 10.2
Pull Request -
State: closed - Opened by kan-bayashi about 3 years ago
#45 - Add mini_librispeech diarization pretrained model
Pull Request -
State: closed - Opened by YushiUeda about 3 years ago
- 1 comment
#44 - Huggingface compatibility
Pull Request -
State: closed - Opened by kamo-naoyuki about 3 years ago
- 1 comment
#43 - Add Ksponspeech pretrained model
Pull Request -
State: closed - Opened by YushiUeda over 3 years ago
- 6 comments
#42 - How to get the decoding result scores from
Issue -
State: open - Opened by pengcheng-tech over 3 years ago
- 4 comments
#41 - Update table.csv
Pull Request -
State: closed - Opened by guoaoo over 3 years ago
- 7 comments
Labels: bug
#40 - Javanese and Sundanese ASR Models
Pull Request -
State: closed - Opened by peter-yh-wu over 3 years ago
- 2 comments
#39 - Huggingface compatibility
Pull Request -
State: closed - Opened by Fhrozen over 3 years ago
- 7 comments
#38 - Update table.csv
Pull Request -
State: closed - Opened by ftshijt over 3 years ago
- 1 comment
#37 - SWBD ESPNet2 Update
Pull Request -
State: closed - Opened by roshansh-cmu over 3 years ago
- 4 comments
#36 - update swbd model
Pull Request -
State: closed - Opened by yuekaizhang over 3 years ago
- 1 comment
#35 - Add dns-ins20 enh pre-trained model
Pull Request -
State: closed - Opened by neillu23 over 3 years ago
- 1 comment
#34 - fallback when not having write permission
Pull Request -
State: closed - Opened by kamo-naoyuki over 3 years ago
- 1 comment
#33 - Request for a default data folder for fallback
Issue -
State: closed - Opened by lumaku over 3 years ago
- 2 comments
#32 - ASR demo multiple threads
Issue -
State: open - Opened by BarryKCL over 3 years ago
- 1 comment
#31 - Is there a Mandarin multi-speaker pretrained model?
Issue -
State: closed - Opened by caohangabc over 3 years ago
- 1 comment
#30 - Update PYPI
Issue -
State: closed - Opened by ftshijt over 3 years ago
- 3 comments
Labels: help wanted
#29 - Add multilingual pre-trained model
Pull Request -
State: closed - Opened by ftshijt over 3 years ago
- 1 comment
#28 - Error when test ASR
Issue -
State: closed - Opened by leijue222 over 3 years ago
- 1 comment
#27 - Update table.csv
Pull Request -
State: closed - Opened by sw005320 over 3 years ago
- 1 comment
#26 - Added streaming transformer ASR model on AISHELL
Pull Request -
State: closed - Opened by eml914 over 3 years ago
- 1 comment
#25 - Update table.csv
Pull Request -
State: closed - Opened by kamo-naoyuki over 3 years ago
- 1 comment
#24 - Update table.csv
Pull Request -
State: closed - Opened by sw005320 over 3 years ago
#23 - update table for enh models
Pull Request -
State: closed - Opened by LiChenda over 3 years ago
- 1 comment
#22 - Is there a pretrained model for source separation/speech enhancement?
Issue -
State: closed - Opened by jnaranjo-sciling over 3 years ago
- 1 comment
#21 - Update model info
Pull Request -
State: closed - Opened by ftshijt over 3 years ago
#20 - Add the model of laborotv.
Pull Request -
State: closed - Opened by jnishi almost 4 years ago
- 1 comment
#19 - Remove community_identifer
Pull Request -
State: closed - Opened by kamo-naoyuki almost 4 years ago
- 1 comment
#18 - Can't load chime4 model
Issue -
State: closed - Opened by JorisCos almost 4 years ago
- 1 comment
#17 - Add JSUT models
Pull Request -
State: closed - Opened by kan-bayashi almost 4 years ago
#16 - Add new multi-speaker pretrained models
Pull Request -
State: closed - Opened by kan-bayashi almost 4 years ago
- 3 comments
#15 - Resource Error with a learnt model.
Issue -
State: closed - Opened by 0h-n0 almost 4 years ago
- 1 comment
Labels: question
#14 - Add new JSUT pretrained models
Pull Request -
State: closed - Opened by kan-bayashi almost 4 years ago
- 1 comment
#13 - Unpacking a local model
Issue -
State: closed - Opened by Daniel-asr almost 4 years ago
- 6 comments
#12 - soundfile.write("out.wav", speech.numpy(), text2speech.fs, "PCM_16") gives an error
Issue -
State: closed - Opened by MikeyBeez about 4 years ago
- 2 comments
Labels: question
#11 - is input.wav's fs must be same to model's fs?
Issue -
State: closed - Opened by lfxx about 4 years ago
- 2 comments
#10 - Packing a trained model
Issue -
State: closed - Opened by Daniel-asr about 4 years ago
- 1 comment
#9 - Add AISHELL model
Pull Request -
State: closed - Opened by kamo-naoyuki about 4 years ago
#8 - Minor documentation update
Pull Request -
State: closed - Opened by sw005320 about 4 years ago
- 3 comments
#7 - Examples of speech tensor shape for gst models?
Issue -
State: closed - Opened by ajbouh about 4 years ago
- 10 comments
Labels: question
#6 - Update table.csv
Pull Request -
State: closed - Opened by kan-bayashi about 4 years ago
- 1 comment
#5 - Update table.csv
Pull Request -
State: closed - Opened by kan-bayashi about 4 years ago
- 1 comment
#4 - Fix model test
Pull Request -
State: closed - Opened by kamo-naoyuki about 4 years ago
- 3 comments
#3 - Add test for registered model
Pull Request -
State: closed - Opened by kamo-naoyuki about 4 years ago
- 1 comment
#2 - Update table.csv
Pull Request -
State: closed - Opened by kamo-naoyuki about 4 years ago
#1 - Add TTS pretrained model
Pull Request -
State: closed - Opened by kan-bayashi over 4 years ago
- 1 comment